24
AI based Microscopy diagnosis of Malaria AI for Health Workshop 2019 Rose Nakasi Makerere University Artificial intelligence and data science Lab 2/9/2019 1 / 24

AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

  • Upload
    others

  • View
    2

  • Download
    0

Embed Size (px)

Citation preview

Page 1: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

AI based Microscopy diagnosis of MalariaAI for Health Workshop 2019

Rose Nakasi

Makerere UniversityArtificial intelligence and data science Lab

2/9/2019

1 / 24

Page 2: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Microscopy Diagnosis

Figure: Gold standard for diagnosis of malaria is a microscope2 / 24

Page 3: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Health diagnostic burden

Currently in Uganda, and many developing countries

• Malaria has beenreported as one of theleading cause of deathaccounting for over27% of lives ofUgandans

• Patient in big numberswait to be diagnosed.

3 / 24

Page 4: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Currently in Uganda, and many developing countries

• Most of these countriesdon’t have enoughtrained lab technicians.

• In Ghana, 1.72microscopes per100,000 population,but only 0.85 trainedlaboratory staff per100,000 population .

4 / 24

Page 5: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Microscopy Diagnostic challenge

Currently in Uganda, and many developing countries

• SOP requires not toview more than 20slides a day

• IMicroscopy is eyestraining

5 / 24

Page 6: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Concept detail

Figure: Adapter set up and attachment.

6 / 24

Page 7: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Concept detail

7 / 24

Page 8: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Concept detail

8 / 24

Page 9: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Captured image

Figure: Malaria microscopic image captured with a smartphone.

9 / 24

Page 10: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Plasmodium detection accuracies

Figure: Plasmodium detection results.

10 / 24

Page 11: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

ROC AUC for malaria, TB and intestinal parasitesdetection

Figure: Deep learning ROC accuracies.

11 / 24

Page 12: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Detected Objects for plasmodium (left) andbacilli(right).

12 / 24

Page 13: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Server end app.

13 / 24

Page 14: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Server end app.

Figure: Before detection.

14 / 24

Page 15: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Server end app.

Figure: After detection.15 / 24

Page 16: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Framework assessment requirements

Reasons to consider for an effective clinical framework;

• Representativeness in data

• Explainability

• Potential biases in the data.

16 / 24

Page 17: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Representativeness in data

Training data is from a different context;

• Obvious case: do not use European training data for medicaldiagnostics in East Africa.

• Less obvious case: Medical diagnostics data could usetraining data from East Africa for an algorithm in WestAfrica – may under-diagnose malaria.

Training data is imbalanced;

• Data that is not balanced in terms of pixel dimensions,shape, color etc may bias certain algorithms to favor certaingroups

17 / 24

Page 18: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Explainability

Ethical coonsiderations;

• Do Organizations think of ethics when using data/outcomesfrom algorithms, resulting organizational values not beingcaptured in outcomes.

Relevancy / Value;

• Should organizations be using AI and does AI provide enoughvalue that offsets potential complications?

Transparency;

• How transparent are the algorithms/outputs?

18 / 24

Page 19: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Potential data Biases

Does your data have biases reflected in it? If so, your algorithms mayamplify these biases;

• Due to poor annotations.

• Different image dimensions.

• Different environments under which the images werecaptured.

19 / 24

Page 20: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

What can we do?

• Auditable algorithms

• Implement fairness

• Accountability and responsibility

20 / 24

Page 21: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Auditable algorithms

Bias is introduced at the algorithm level

• Developers are making decisions to choose between equity,accuracy, speed

Ensure that algorithms are auditable;

• Can they be monitored by external actors? How can you testthe algorithms?

21 / 24

Page 22: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Fairness

Data will never be perfect. How will we deal with imperfect data?

• Getting better data

• Implementing fairness/equity at the algorithm level

22 / 24

Page 23: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Accountability and responsibility

What mechanisms can we add to make sure that we are holding ourselvesand algorithms accountable?

• We work in complex situations and downstream effects arehard to predict

• Build in monitoring to make sure that we can adapt to andfix inequalities that result

• Above all, an AI Assessment Framework to guide AI forhealth Solutions.

23 / 24

Page 24: AI based Microscopy diagnosis of Malaria · Malaria has been reported as one of the leading cause of death accounting for over 27% of lives of Ugandans Patient in big numbers wait

Thank you!

Questions?

24 / 24